harness-visualizer

Architectural compliance and code quality rules for Node.js + TypeScript projects (Vue 3 frontend, Express + Socket.IO backend). Provides systematic review criteria for security, code organization, error handling, and project-specific conventions. Use when auditing code quality.

Mutation testing strategies and test-improvement patterns for TypeScript projects using Stryker Mutator with a Vitest runner. Provides guidance on interpreting mutation reports and improving tests to achieve higher kill rates. Use when analyzing mutation testing results.

Risk identification and test prioritization framework for Node.js + TypeScript projects (Vue 3 + Express + Socket.IO). Provides systematic approach to identifying potential issues and prioritizing testing efforts. Use when analyzing features for QA review.

Parses specification documents (EARS, Given-When-Then, SHALL clauses, user stories, tasks) from multiple layouts into a structured intermediate representation, then maps requirements to tests bidirectionally. Use when verifying implementation against a spec, auditing requirement coverage, or computing a traceability matrix.

Vitest testing patterns and templates for Node.js + TypeScript projects (Express backend, Vue 3 frontend). Provides comprehensive test writing guidance for unit, integration, component, and property-based tests. Use when generating or improving tests for the harness-visualizer.

Browser automation for web projects using playwright-cli

Indexes, searches, and injects project spec files as agent memory. Use when starting work on a spec-driven project, searching for relevant specs, recalling past design decisions, archiving spec changes, or checking spec history. Supports both directory-style specs (specs/<name>/requirements.md|design.md|tasks.md) and flat-style specs (.claude/specs/active/<name>.md).

Multi-agent implementation team for parallel code execution. Transforms specs, task descriptions, and feature requests into working code using coordinated Agent Teams with an Opus lead and Sonnet teammates. Supports parallel implementation, architect review, test writing, and external research via Perplexity MCP. Keywords: implementation, agent-teams, parallel, orchestration, code-review, testing, spec, feature, multi-agent.

Specification generation pipeline for software projects. Transforms discovery collateral (meeting transcripts, Linear issues, Slack threads, deep research documents, user conversations) into implementation-ready specifications. Uses Agent Teams for parallel codebase research and a composable phase pipeline with validation gates between phases. Keywords: spec, specification, requirements, design, tasks, discovery, research, pipeline, transcript, planning, EARS, technical design.

Single-agent spec implementation workflow for harness-visualizer. Use when asked to implement a spec, execute tasks from specs/, continue spec work, complete a phase/wave, or turn an implementation-ready requirements/design/tasks bundle into working TypeScript code (Vue 3 frontend, Express + Socket.IO backend). Adapted from the Claude Build plugin's implementation-team knowledge without multi-agent orchestration.